# LRR‐UNet: A Deep Unfolding Network With Low‐Rank Recovery for EEG Signal Denoising

## TL;DR

This paper introduces LRR-UNet, a deep learning model that combines the strengths of traditional signal processing with deep learning to improve EEG signal denoising and interpretability.

## Contribution

The novel contribution is the development of LRR-UNet, a deep unfolding network that integrates low-rank recovery theory with deep learning for EEG denoising.

## Key findings

- LRR-UNet outperforms state-of-the-art models in removing ocular and electromyographic artifacts from EEG signals.
- EEG signals preprocessed with LRR-UNet show better performance in downstream classification tasks.
- The model achieves superior results on both quantitative and qualitative metrics.

## Abstract

Electroencephalogram (EEG) signals are crucial for brain–computer interface research but are highly susceptible to noise contamination, necessitating effective denoising. While deep learning has been widely applied, its “black‐box” nature limits interpretability. In contrast, traditional model‐based methods like Low‐Rank Recovery (LRR) offer strong interpretability by decomposing signals into low‐rank and sparse components.

This paper aims to develop an interpretable deep‐learning model for EEG denoising that combines the performance of deep learning with the interpretability of traditional LRR methods.

We propose LRR‐Unet, a deep unfolding network that transforms the traditional iterative LRR algorithm into a neural network architecture. Specifically, the time‐consuming Singular Value Decomposition (SVD) and sparse optimization processes in LRR are replaced with learnable neural network modules.

Extensive experiments demonstrate that LRR‐Unet outperforms other state‐of‐the‐art models in removing ocular and electromyographic artifacts, achieving superior performance on both quantitative and qualitative metrics. Furthermore, in downstream classification tasks, EEG signals preprocessed with LRR‐Unet yield better results across various evaluation indicators.

The proposed LRR‐Unet provides an effective and interpretable solution for EEG denoising. Its superiority in denoising performance and practical utility in enhancing downstream application performance is validated through comprehensive experiments.

Drawing on the intrinsic properties of EEG signals and noise, we developed an EEG denoising algorithm that integrates low‐rank recovery theory with deep learning. Supported by a physical model, this algorithm demonstrates superior denoising performance on relevant datasets.